Yi-Coder 9B
01.AI's Apache-2.0 bilingual code model — strong 9B coding with 128K context.
About
Yi-Coder-9B-Chat (September 2024) is 01.AI's bilingual Chinese/English code model: 9B parameters, 128K context, trained on 10T tokens with strong code generation and reasoning.
Apache 2.0 licensed — commercial use allowed. 9.8k Hugging Face downloads. At release it was competitive with much larger code models on HumanEval/MBPP-style evaluations (provider-reported). A 2024 model now superseded by Qwen2.5-Coder-7B in the same size class, but the Apache-2.0 terms and bilingual strength keep it viable for Chinese-English codebases.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-claimed at release (2024): competitive HumanEval/MBPP for 9B — treat as provider-claimed and dated. No current leaderboard presence.
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 6/10
Scored 6/10 (metrics tier). Apache 2.0, bilingual, 128K context — a well-rounded 2024 code model. Docked four points: (1) superseded by Qwen2.5-Coder-7B in the same class; (2) benchmark claims are dated provider reports; (3) modest adoption (9.8k HF downloads); (4) 01.AI's model lineup has moved on. Solid for bilingual codebases; not a current leader.
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 6.2/10
- Maintenance · recency, releases, issue load
- 4.0/10
- Openness · license + docs
- 8.8/10
- Manual review · sanity read + red-flag check
- 6.0/10
- · HF downloads 9,838 (peer-normalized)
- · released 768 days ago
- · manual review: bilingual, 128K context; superseded by Qwen2.5-Coder-7B; dated provider benchmarks; license: Apache-2.0